Doc
nexu-io/open-design
Read, create, and edit .docx documents with formatting and layout fidelity via OpenAI's document skill.
A skill your agent uses when 特性开发需要直接在产品仓库 docs/features 下写可评审的特性文档和邻近设计文档。
$ npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-doc-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/nucleus/skills/feature-doc-design .claude/skills/feature-doc-design && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "feature-doc-design" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-doc-design into .claude/skills/feature-doc-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-doc-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-doc-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-doc-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/nucleus/skills/feature-doc-design .agents/skills/feature-doc-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "feature-doc-design" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-doc-design into .agents/skills/feature-doc-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-doc-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-doc-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/nucleus/skills/feature-doc-design .cursor/skills/feature-doc-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "feature-doc-design" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-doc-design into .cursor/skills/feature-doc-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-doc-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/protect-my-hair/nucleus-marketplace.git --path plugins/nucleus/skills/feature-doc-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-doc-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/nucleus/skills/feature-doc-design .gemini/skills/feature-doc-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "feature-doc-design" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-doc-design into .gemini/skills/feature-doc-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-doc-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install protect-my-hair/nucleus-marketplace feature-doc-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/nucleus/skills/feature-doc-design .github/skills/feature-doc-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "feature-doc-design" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-doc-design into .github/skills/feature-doc-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-doc-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-doc-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/nucleus/skills/feature-doc-design .opencode/skills/feature-doc-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "feature-doc-design" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-doc-design into .opencode/skills/feature-doc-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-doc-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
feature-doc-designA skill your agent uses when 特性开发需要直接在产品仓库 docs/features 下写可评审的特性文档和邻近设计文档。
Feature Doc Design is an agent skill from protect-my-hair/nucleus-marketplace. Use when 特性开发需要直接在产品仓库 docs/features 下写可评审的特性文档和邻近设计文档。
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/feature-doc-design-manifest-template.json` and `assets/nucleus-feature-doc-design-manifest.schema.json`).
The repository describes itself as: Nucleus — Claude Code / Codex 工作流插件,确保 AI 编码产出结构可信、边界可审计、过程可追溯. The licence is MIT.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 3c82085. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Feature Doc Design loads about 895 tokens when it runs, and up to ~1k if it reads all its reference files. Until then it costs about 19 tokens; SKILL.md has 218 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from protect-my-hair/nucleus-marketplace at commit 3c82085, republished under its MIT licence (© protect-my-hair). 218 words, ~895 tokens.
.claude/skills/feature-doc-design/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.前置:使用本 Skill 前,先按
using-nucleus完成 Nucleus 入口识别(Claude Code 会话由插件 SessionStart hook 自动注入该纪律)。
特性设计先服务产品能力表达,再服务实现计划;设计未被人工评审接受前,不得进入计划、代码或测试。
<HARD-GATE>
未读取当前特性输入、需求设计 / 特性拆解证据和目标 `docs/features/**` 结构,或设计未获得人工评审事实时,不得写实施计划、源码、测试或正式交付证据。
请求人工设计评审前,必须先按 _shared/references/subagent-precheck-protocol.md 执行 subagentPreReview 子代理预审;未取得“材料可提交人工审查”结论时,不得请求人工接受设计。
</HARD-GATE>
使用本 Skill:特性开发中本 Skill 是每个特性的第一个领域步骤,把当前特性收口为产品仓库里可评审的特性文档和邻近设计文档;必须用当前产品既有 docs/features/** 结构和邻近设计约定作为目标形态,让设计成为可评审 Git diff。
不要使用本 Skill:自创临时特性设计格式或把实现计划混入特性设计产物;写需求设计、源码、测试、提交、推送、PR、发布或缺陷状态变更;在设计获人工评审接受前生成实施计划、源码、测试或正式交付证据。
启动本 Skill 后,必须先为每一项创建宿主 todo/task,并按顺序逐项推进、逐项更新状态;Codex 使用计划 / 任务工具,Claude Code 使用 TodoWrite 或等价宿主 todo。.nucleus/runs/**、summary.md、result.json、候选文件和 review report 只能记录事实,不能替代宿主任务、预审或人工设计评审事实。
读取 context 和当前特性输入
完成证据:已读 .nucleus/context/<workflowRunId>.json,并确认恰好一个已存在的 primary docs/features/**/feature.md,或一个 schema 合法、带 candidateFeaturePath 的 mapping candidate。
STOP:primary 特性歧义、缺输入、受保护写入、legacy 路径、路径逃逸或 schema 失败时 FAILED_BLOCKED;缺当前特性输入时 ALERT_AND_BLOCK。
读取目标产品既有 docs/features/** 结构和邻近设计约定
完成证据:当前特性的目标放置路径与邻近设计文档约定记录。
STOP:缺目标 docs/features/** 放置证据时 ALERT_AND_BLOCK,不得自创临时特性设计格式。
读取需求设计 / 特性拆解证据
完成证据:相关需求设计与 requirement-decomposition 拆解证据引用。
STOP:特性开发调用时缺需求设计或特性拆解输入时 ALERT_AND_BLOCK。
创建宿主特性设计任务包
完成证据:覆盖本 Checklist 各项的宿主 todo/task。
STOP:未建宿主任务包时,不得写 docs/features/** 或调度预审。
写可评审特性文档到 docs/features/**
完成证据:已读取 _shared/references/design-visualization-discipline.md,按当前特性输入判断是否需要 Mermaid 图示;复杂设计使用合适图示说明业务流、数据流、状态、实体关系或跨系统时序,简单设计明确不需要图示;只读 candidateFeaturePath 时创建目标 feature.md 和同叶子设计文档;写出可评审 docs/features 变更后状态为待评审。
STOP:任何请求在设计评审前生成实施计划或代码时 ALERT_AND_BLOCK;不得把 feature design 和 implementation plan 写进同一候选产物。
按共享协议执行人审前预审
完成证据:独立 reviewer 子代理 subagentPreReview 输出“材料可提交人工审查”,blocking / important 已整改复核。
STOP:按 _shared/references/subagent-precheck-protocol.md 执行预审;未取得材料可提交人工审查结论前不得请求人工评审。
请求人工设计评审
完成证据:人工评审或明确 PMS 评审事实接受设计。
STOP:向人请求设计评审前必须已有 subagentPreReview 且材料可提交人工审查;按 _shared/references/interaction-format.md 的确认型格式呈现;评审接受前不得写实施计划、源码、测试或正式交付证据。
写 result package
完成证据:写出可评审 docs/features 变更后返回 NEEDS_HUMAN_REVIEW。
STOP:.ac manifest / summary / result 只记录过程事实,不得代替人工设计评审事实。
可评审产品文档只写到 docs/features/**;过程证据、gate、manifest、blocker、result 只写到 .nucleus/runs/<workflowRunId>/。本 Skill 不写 docs/requirement/**、源码、测试、提交、推送、PR、发布或缺陷状态变更。写出可评审变更时返回 NEEDS_HUMAN_REVIEW;primary 特性歧义、缺输入、受保护写入、legacy 路径、路径逃逸或 schema 失败时返回 FAILED_BLOCKED。
docs/features/** 既有结构。.ac manifest、summary 或 result 代替人工设计评审事实。docs/features/** 结构就写设计。summary.md、result.json 写成人工已接受。python3 skills/feature-doc-design/scripts/feature_doc_design.py design \
--repo-root <target-repo> \
--context <target-repo>/.nucleus/context/<workflowRunId>.jsonruntime 只引用打包 Skill 资产和 skills/_shared/nucleus_runtime/,不引用 root harness/ 或 root scripts/。脚本失败、依赖缺失或 context 不满足时必须阻塞并记录原因,不得手工模拟正常产物。
© protect-my-hair, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (scripts, references, assets) in plugins/nucleus/skills/feature-doc-design of protect-my-hair/nucleus-marketplace.
Open the folder on GitHubat commit 3c82085
Feature Doc Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Feature Doc Design this skillprotect-my-hair/nucleus-marketplace | 164 | — | ~895 | Automated safety check: Pass | MIT | |
| Docnexu-io/open-design | 100k | — | ~266 | Automated safety check: Pass | Apache-2.0 | |
| Doctermio-sh/termio | 539 | — | ~2k | Automated safety check: Pass | MIT | |
| Docboshu2/agentops | 448 | 1 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Dockv0906/pm-kit | 138 | — | ~472 | Automated safety check: Notes | MIT | |
| DocleanEthereum/leanSpec | 143 | — | ~1.9k | Automated safety check: Pass | MIT |
nexu-io/open-design
Read, create, and edit .docx documents with formatting and layout fidelity via OpenAI's document skill.
termio-sh/termio
A skill your agent uses for ANY operation on a doc under docs/ — creating, updating/editing, changing its status, or querying.
boshu2/agentops
Write or update READMEs, docs, repo instructions and handoff notes, checked against source.
kv0906/pm-kit
Draft or edit a document — PRD, spec, design doc, technical brief.
leanEthereum/leanSpec
Document code in this repository.
Sikao-Engine/KimiX
Guide for navigating and maintaining Kimix project documentation.
protect-my-hair/nucleus-marketplace
Collects prior Nucleus task evidence into a candidate-only delivery closure package and PR/MR draft text, blocking if any feature's design, review or verification evidence is missing.
protect-my-hair/nucleus-marketplace
Validates the context file for a Nucleus V2 workflow run, discovers standalone context from explicit input, and writes a blocked result when required context is missing.
protect-my-hair/nucleus-marketplace
Collects, freezes and validates a Nucleus V2 session binding report that records the native Claude Code or Codex session ID, transcript path and hash.
protect-my-hair/nucleus-marketplace
Builds the result.json file for a Nucleus V2 workflow run from its context, gates, blockers and step status, and exits non-zero when the run is blocked.
protect-my-hair/nucleus-marketplace
Checks whether a defect report has enough context to be accepted, then drafts candidate-only root-cause evidence for human review without confirming causes or changing code.
protect-my-hair/nucleus-marketplace
Combines the evidence from completed Nucleus workflow steps into a final evidence report and result package, without scheduling steps, updating trackers or opening pull requests.
A skill your agent uses when 特性开发需要直接在产品仓库 docs/features 下写可评审的特性文档和邻近设计文档。. Feature Doc Design is an agent skill from protect-my-hair/nucleus-marketplace.
Feature Doc Design fits situations like: 特性开发需要直接在产品仓库 docs/features 下写可评审的特性文档和邻近设计文档.
Run `npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a claude-code`. Or copy the skill folder (plugins/nucleus/skills/feature-doc-design in protect-my-hair/nucleus-marketplace) into .claude/skills/feature-doc-design in your project. Claude Code loads it when a task matches its description.
Run `npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a codex`. Or copy the skill folder (plugins/nucleus/skills/feature-doc-design in protect-my-hair/nucleus-marketplace) into .agents/skills/feature-doc-design in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add protect-my-hair/nucleus-marketplace --skill feature-doc-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-doc-design, .gemini/skills/feature-doc-design, .github/skills/feature-doc-design and .opencode/skills/feature-doc-design in your project.
Going by SKILL.md and its folder, Feature Doc Design needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Feature Doc Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 895 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 139 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Feature Doc Design: Doc (nexu-io/open-design, 100k stars), Doc (termio-sh/termio, 539 stars), Doc (boshu2/agentops, 448 stars) and Doc (kv0906/pm-kit, 138 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
protect-my-hair (a GitHub user) maintains it in protect-my-hair/nucleus-marketplace, which has 164 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on July 23, 2026.
Source: protect-my-hair/nucleus-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.